Image segmentation is one of the most fundamental problems in computer vision and has drawn a lot of attentions due to its vast applications in image understanding and autonomous driving. However, designing effective and efficient segmentation neural architectures is a labor-intensive process that may require lots of trials by human experts. In this paper, we address the challenge of integrating multi-head self-attention into high resolution representation CNNs efficiently, by leveraging architecture search. Manually replacing convolution layers with multi-head self-attention is non-trivial due to the costly overhead in memory to maintain high resolution. By contrast, we develop a multi-target multi-branch supernet method, which not only fully utilizes the advantages of high-resolution features, but also finds the proper location for placing multi-head self-attention module. Our search algorithm is optimized towards multiple objective s (e.g., latency and mIoU) and capable of finding architectures on Pareto frontier with arbitrary number of branches in a single search. We further present a series of model via Hybrid Convolutional-Transformer Architecture Search (HyCTAS) method that searched for the best hybrid combination of light-weight convolution layers and memory-efficient self-attention layers between branches from different resolutions and fuse to high resolution for both efficiency and effectiveness. Extensive experiments demonstrate that HyCTAS outperforms previous methods on semantic segmentation task. Code and models are available at \url{https://github.com/MarvinYu1995/HyCTAS}.
We introduce Florence-2, a novel vision foundation model with a unified, prompt-based representation for a variety of computer vision and vision-language tasks. While existing large vision models excel in transfer learning, they struggle to perform a diversity of tasks with simple instructions, a capability that implies handling the complexity of various spatial hierarchy and semantic granularity. Florence-2 was designed to take text-prompt as task instructions and generate desirable results in text forms, whether it be captioning, object detection, grounding or segmentation. This multi-task learning setup demands large-scale, high-quality annotated data. To this end, we co-developed FLD-5B that consists of 5.4 billion comprehensive visual annotations on 126 million images, using an iterative strategy of automated image annotation and model refinement. We adopted a sequence-to-sequence structure to train Florence-2 to perform versatile and comprehensive vision tasks. Extensive evaluations on numerous tasks demonstrated Florence-2 to be a strong vision foundation model contender with unprecedented zero-shot and fine-tuning capabilities.
In this paper, we introduce an intriguing phenomenon-the successful reconstruction of images using a set of one-way wave equations with hidden and learnable speeds. Each individual image corresponds to a solution with a unique initial condition, which can be computed from the original image using a visual encoder (e.g., a convolutional neural network). Furthermore, the solution for each image exhibits two noteworthy mathematical properties: (a) it can be decomposed into a collection of special solutions of the same one-way wave equations that are first-order autoregressive, with shared coefficient matrices for autoregression, and (b) the product of these coefficient matrices forms a diagonal matrix with the speeds of the wave equations as its diagonal elements. We term this phenomenon hidden waves, as it reveals that, although the speeds of the set of wave equations and autoregressive coefficient matrices are latent, they are both learnable and shared across images. This represents a mathematical invariance across images, providing a new mathematical perspective to understand images.
End-to-end Transformers have demonstrated an impressive success rate for Embodied Instruction Following when the environment has been seen in training. However, they tend to struggle when deployed in an unseen environment. This lack of generalizability is due to the agent's insensitivity to subtle changes in natural language instructions. To mitigate this issue, we propose explicitly aligning the agent's hidden states with the instructions via contrastive learning. Nevertheless, the semantic gap between high-level language instructions and the agent's low-level action space remains an obstacle. Therefore, we further introduce a novel concept of meta-actions to bridge the gap. Meta-actions are ubiquitous action patterns that can be parsed from the original action sequence. These patterns represent higher-level semantics that are intuitively aligned closer to the instructions. When meta-actions are applied as additional training signals, the agent generalizes better to unseen environments. Compared to a strong multi-modal Transformer baseline, we achieve a significant 4.5% absolute gain in success rate in unseen environments of ALFRED Embodied Instruction Following. Additional analysis shows that the contrastive objective and meta-actions are complementary in achieving the best results, and the resulting agent better aligns its states with corresponding instructions, making it more suitable for real-world embodied agents. The code is available at: https://github.com/joeyy5588/LACMA.
Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces limited results due to (1) semantic ambiguity -- an image-level label only captures a salient part of the image, ignoring the remaining rich semantics within the image; and (2) location sensitivity -- the label highly depends on the locations and crops of the original image, which may change after data transformations like random cropping. To remedy this, we propose RichSem, a simple but effective method, which is robust to learn rich semantics from coarse locations without the need of accurate bounding boxes. RichSem leverages rich semantics from images, which are then served as additional soft supervision for training detectors. Specifically, we add a semantic branch to our detector to learn these soft semantics and enhance feature representations for long-tailed object detection. The semantic branch is only used for training and is removed during inference. RichSem achieves consistent improvements on both overall and rare-category of LVIS under different backbones and detectors. Our method achieves state-of-the-art performance without requiring complex training and testing procedures. Moreover, we show the effectiveness of our method on other long-tailed datasets with additional experiments. Code is available at \url{https://github.com/MengLcool/RichSem}.
This paper reveals that every image can be understood as a first-order norm+linear autoregressive process, referred to as FINOLA, where norm+linear denotes the use of normalization before the linear model. We demonstrate that images of size 256$\times$256 can be reconstructed from a compressed vector using autoregression up to a 16$\times$16 feature map, followed by upsampling and convolution. This discovery sheds light on the underlying partial differential equations (PDEs) governing the latent feature space. Additionally, we investigate the application of FINOLA for self-supervised learning through a simple masked prediction technique. By encoding a single unmasked quadrant block, we can autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves effective for image classification and object detection tasks, even in lightweight networks, without requiring fine-tuning. The code will be made publicly available.
Existing deep video models are limited by specific tasks, fixed input-output spaces, and poor generalization capabilities, making it difficult to deploy them in real-world scenarios. In this paper, we present our vision for multimodal and versatile video understanding and propose a prototype system, \system. Our system is built upon a tracklet-centric paradigm, which treats tracklets as the basic video unit and employs various Video Foundation Models (ViFMs) to annotate their properties e.g., appearance, motion, \etc. All the detected tracklets are stored in a database and interact with the user through a database manager. We have conducted extensive case studies on different types of in-the-wild videos, which demonstrates the effectiveness of our method in answering various video-related problems. Our project is available at https://www.wangjunke.info/ChatVideo/
Object tracking (OT) aims to estimate the positions of target objects in a video sequence. Depending on whether the initial states of target objects are specified by provided annotations in the first frame or the categories, OT could be classified as instance tracking (e.g., SOT and VOS) and category tracking (e.g., MOT, MOTS, and VIS) tasks. Combing the advantages of the best practices developed in both communities, we propose a novel tracking-with-detection paradigm, where tracking supplements appearance priors for detection and detection provides tracking with candidate bounding boxes for association. Equipped with such a design, a unified tracking model, OmniTracker, is further presented to resolve all the tracking tasks with a fully shared network architecture, model weights, and inference pipeline. Extensive experiments on 7 tracking datasets, including LaSOT, TrackingNet, DAVIS16-17, MOT17, MOTS20, and YTVIS19, demonstrate that OmniTracker achieves on-par or even better results than both task-specific and unified tracking models.
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them is far from success. In this paper, we start by making the empirical observation that a naive joint optimization of CL and MIM losses leads to conflicting gradient directions - more severe as the layers go deeper. This motivates us to shift the paradigm from combining loss at the end, to choosing the proper learning method per network layer. Inspired by experimental observations, we find that MIM and CL are suitable to lower and higher layers, respectively. We hence propose to combine them in a surprisingly simple, "sequential cascade" fashion: early layers are first trained under one MIM loss, on top of which latter layers continue to be trained under another CL loss. The proposed Layer Grafted Pre-training learns good visual representations that demonstrate superior label efficiency in downstream applications, in particular yielding strong few-shot performance besides linear evaluation. For instance, on ImageNet-1k, Layer Grafted Pre-training yields 65.5% Top-1 accuracy in terms of 1% few-shot learning with ViT-B/16, which improves MIM and CL baselines by 14.4% and 2.1% with no bells and whistles. The code is available at https://github.com/VITA-Group/layerGraftedPretraining_ICLR23.git.